CVPR 2024 Papers

Few-shot segmentation remains challenging due to the limitations of its labeling information for unseen classes. Most previous approaches rely on extracting high-level feature maps from the frozen visual encoder to compute the pixel-wise similarity as a key prior guidance for the decoder. However such a prior representation suffers from coarse granularity and poor generalization to new classes since these high-level feature maps have obvious category bias. In this work we propose to replace the visual prior representation with the visual-text alignment capacity to capture more reliable guidance and enhance the model generalization. Specifically we design two kinds of training-free prior information generation strategy that attempts to utilize the semantic alignment capability of the Contrastive Language-Image Pre-training model (CLIP) to locate the target class. Besides to acquire more accurate prior guidance we build a high-order relationship of attention maps and utilize it to refine the initial prior information. Experiments on both the PASCAL-5i and COCO-20i datasets show that our method obtains a clearly substantial improvement and reaches the new state-of-the-art performance. The code is available on the project website.

Multi-view representation learning aims to derive robust representations that are both view-consistent and view-specific from diverse data sources. This paper presents an in-depth analysis of existing approaches in this domain highlighting a commonly overlooked aspect: the redundancy between view-consistent and view-specific representations. To this end we propose an innovative framework for multi-view representation learning which incorporates a technique we term 'distilled disentangling'. Our method introduces the concept of masked cross-view prediction enabling the extraction of compact high-quality view-consistent representations from various sources without incurring extra computational overhead. Additionally we develop a distilled disentangling module that efficiently filters out consistency-related information from multi-view representations resulting in purer view-specific representations. This approach significantly reduces redundancy between view-consistent and view-specific representations enhancing the overall efficiency of the learning process. Our empirical evaluations reveal that higher mask ratios substantially improve the quality of view-consistent representations. Moreover we find that reducing the dimensionality of view-consistent representations relative to that of view-specific representations further refines the quality of the combined representations.

Multi-domain generalization (mDG) is universally aimed to minimize the discrepancy between training and testing distributions to enhance marginal-to-label distribution mapping. However existing mDG literature lacks a general learning objective paradigm and often imposes constraints on static target marginal distributions. In this paper we propose to leverage a Y-mapping to relax the constraint. We rethink the learning objective for mDG and design a new general learning objective to interpret and analyze most existing mDG wisdom. This general objective is bifurcated into two synergistic amis: learning domain-independent conditional features and maximizing a posterior. Explorations also extend to two effective regularization terms that incorporate prior information and suppress invalid causality alleviating the issues that come with relaxed constraints. We theoretically contribute an upper bound for the domain alignment of domain-independent conditional features disclosing that many previous mDG endeavors actually optimize partially the objective and thus lead to limited performance. As such our study distills a general learning objective into four practical components providing a general robust and flexible mechanism to handle complex domain shifts. Extensive empirical results indicate that the proposed objective with Y-mapping leads to substantially better mDG performance in various downstream tasks including regression segmentation and classification. Code is available at https://github.com/zhaorui-tan/GMDG/tree/main.

The goal of interactive image segmentation is to delineate specific regions within an image via visual or language prompts. Low-latency and high-quality interactive segmentation with diverse prompts remain challenging for existing specialist and generalist models. Specialist models with their limited prompts and task-specific designs experience high latency because the image must be recomputed every time the prompt is updated due to the joint encoding of image and visual prompts. Generalist models exemplified by the Segment Anything Model (SAM) have recently excelled in prompt diversity and efficiency lifting image segmentation to the foundation model era. However for high-quality segmentations SAM still lags behind state-of-the-art specialist models despite SAM being trained with x100 more segmentation masks. In this work we delve deep into the architectural differences between the two types of models. We observe that dense representation and fusion of visual prompts are the key design choices contributing to the high segmentation quality of specialist models. In light of this we reintroduce this dense design into the generalist models to facilitate the development of generalist models with high segmentation quality. To densely represent diverse visual prompts we propose to use a dense map to capture five types: clicks boxes polygons scribbles and masks. Thus we propose SegNext a next-generation interactive segmentation approach offering low latency high quality and diverse prompt support. Our method outperforms current state-of-the-art methods on HQSeg-44K and DAVIS quantitatively and qualitatively.

Despite the growing demand for accurate surface normal estimation models existing methods use general-purpose dense prediction models adopting the same inductive biases as other tasks. In this paper we discuss the inductive biases needed for surface normal estimation and propose to (1) utilize the per-pixel ray direction and (2) encode the relationship between neighboring surface normals by learning their relative rotation. The proposed method can generate crisp - yet piecewise smooth - predictions for challenging in-the-wild images of arbitrary resolution and aspect ratio. Compared to a recent ViT-based state-of-the-art model our method shows a stronger generalization ability despite being trained on an orders of magnitude smaller dataset. The code is available at https://github.com/baegwangbin/DSINE.

Long-term and accurate forecasting is the long-standing pursuit of the human motion prediction task. Existing methods typically suffer from dramatic degradation in prediction accuracy with the increasing prediction horizon. It comes down to two reasons:1? Insufficient numerical stability.Unforeseen high noise and complex feature relationships in the data. 2? Inadequate modeling stability. Unreasonable step sizes and undesirable parameter updates in the prediction.In this paper we design a novel and symplectic integral-inspired framework named symplectic integral neural network (SINN) which engages symplectic trajectories to optimize the pose representation and employs a stable symplectic operator to alternately model the dynamic context. Specifically we design a Symplectic Representation Encoder that performs on enhanced human pose representation to obtain trajectories on the symplectic manifold ensuring numerical stability based on Hamiltonian mechanics and symplectic spatial splitting algorithm. We further present the Symplectic Temporal Aggregation module in the light of the symplectic temporal splitting algorithm which splits the long-term prediction into multiple accurate short-term predictions generated by a symplectic operator to secure modeling stability. Moreover our approach is model-agnostic and can be efficiently integrated with different physical dynamics models.The experimental results demonstrate that our method achieves the new state-of-the-art outperforming existing methods by large margins:20.1%on Human3.6M16.7%on CUM Mocap and 10.2% on 3DPW.

This paper revisits few-shot 3D point cloud semantic segmentation (FS-PCS) with a focus on two significant issues in the state-of-the-art: foreground leakage and sparse point distribution. The former arises from non-uniform point sampling allowing models to distinguish the density disparities between foreground and background for easier segmentation. The latter results from sampling only 2048 points limiting semantic information and deviating from the real-world practice. To address these issues we introduce a standardized FS-PCS setting upon which a new benchmark is built. Moreover we propose a novel FS-PCS model. While previous methods are based on feature optimization by mainly refining support features to enhance prototypes our method is based on correlation optimization referred to as Correlation Optimization Segmentation (COSeg). Specifically we compute Class-specific Multi-prototypical Correlation (CMC) for each query point representing its correlations to category prototypes. Then we propose the Hyper Correlation Augmentation (HCA) module to enhance CMC. Furthermore tackling the inherent property of few-shot training to incur base susceptibility for models we propose to learn non-parametric prototypes for the base classes during training. The learned base prototypes are used to calibrate correlations for the background class through a Base Prototypes Calibration (BPC) module. Experiments on popular datasets demonstrate the superiority of COSeg over existing methods. The code is available at github.com/ZhaochongAn/COSeg.

Recently diffusion models (DM) have been applied in magnetic resonance imaging (MRI) super-resolution (SR) reconstruction exhibiting impressive performance especially with regard to detailed reconstruction. However the current DM-based SR reconstruction methods still face the following issues: (1) They require a large number of iterations to reconstruct the final image which is inefficient and consumes a significant amount of computational resources. (2) The results reconstructed by these methods are often misaligned with the real high-resolution images leading to remarkable distortion in the reconstructed MR images. To address the aforementioned issues we propose an efficient diffusion model for multi-contrast MRI SR named as DiffMSR. Specifically we apply DM in a highly compact low-dimensional latent space to generate prior knowledge with high-frequency detail information. The highly compact latent space ensures that DM requires only a few simple iterations to produce accurate prior knowledge. In addition we design the Prior-Guide Large Window Transformer (PLWformer) as the decoder for DM which can extend the receptive field while fully utilizing the prior knowledge generated by DM to ensure that the reconstructed MR image remains undistorted. Extensive experiments on public and clinical datasets demonstrate that our DiffMSR outperforms state-of-the-art methods.

Oriented object detection has been developed rapidly in the past few years where rotation equivariance is crucial for detectors to predict rotated boxes. It is expected that the prediction can maintain the corresponding rotation when objects rotate but severe mutation in angular prediction is sometimes observed when objects rotate near the boundary angle which is well-known boundary discontinuity problem. The problem has been long believed to be caused by the sharp loss increase at the angular boundary and widely used joint-optim IoU-like methods deal with this problem by loss-smoothing. However we experimentally find that even state-of-the-art IoU-like methods actually fail to solve the problem. On further analysis we find that the key to solution lies in encoding mode of the smoothing function rather than in joint or independent optimization. In existing IoU-like methods the model essentially attempts to fit the angular relationship between box and object where the break point at angular boundary makes the predictions highly unstable. To deal with this issue we propose a dual-optimization paradigm for angles. We decouple reversibility and joint-optim from single smoothing function into two distinct entities which for the first time achieves the objectives of both correcting angular boundary and blending angle with other parameters. Extensive experiments on multiple datasets show that boundary discontinuity problem is well-addressed. Moreover typical IoU-like methods are improved to the same level without obvious performance gap. The code is available at https://github.com/hangxu-cv/cvpr24acm.

Continual learning methods are known to suffer from catastrophic forgetting a phenomenon that is particularly hard to counter for methods that do not store exemplars of previous tasks. Therefore to reduce potential drift in the feature extractor existing exemplar-free methods are typically evaluated in settings where the first task is significantly larger than subsequent tasks. Their performance drops drastically in more challenging settings starting with a smaller first task. To address this problem of feature drift estimation for exemplar-free methods we propose to adversarially perturb the current samples such that their embeddings are close to the old class prototypes in the old model embedding space. We then estimate the drift in the embedding space from the old to the new model using the perturbed images and compensate the prototypes accordingly. We exploit the fact that adversarial samples are transferable from the old to the new feature space in a continual learning setting. The generation of these images is simple and computationally cheap. We demonstrate in our experiments that the proposed approach better tracks the movement of prototypes in embedding space and outperforms existing methods on several standard continual learning benchmarks as well as on fine-grained datasets. Code is available at https://github.com/dipamgoswami/ADC.

With the recent advances in vision transformers and large language models (LLMs) finetuning costly large models on downstream learning tasks poses significant challenges under limited computational resources. This paper presents a REsource and ComputAtion-efficient Pruning framework (RECAP) for the finetuning of transformer-based large models. RECAP by design bridges the gap between efficiency and performance through an iterative process cycling between pruning finetuning and updating stages to explore different chunks of the given large-scale model. At each iteration we first prune the model with Taylor-approximation-based importance estimation and then only update a subset of the pruned model weights based on the Fisher-information criterion. In this way RECAP achieves two synergistic and yet conflicting goals: reducing the GPU memory footprint while maintaining model performance unlike most existing pruning methods that require the model to be finetuned beforehand for better preservation of model performance. We perform extensive experiments with a wide range of large transformer-based architectures on various computer vision and natural language understanding tasks. Compared to recent pruning techniques we demonstrate that RECAP offers significant improvements in GPU memory efficiency capable of reducing the footprint by up to 65%.

Single-photon Light Detection and Ranging (LiDAR) systems are often equipped with an array of detectors for improved spatial resolution and sensing speed. However given a fixed amount of flux produced by the laser transmitter across the scene the per-pixel Signal-to-Noise Ratio (SNR) will decrease when more pixels are packed in a unit space. This presents a fundamental trade-off between the spatial resolution of the sensor array and the SNR received at each pixel. Theoretical characterization of this fundamental limit is explored. By deriving the photon arrival statistics and introducing a series of new approximation techniques the Mean Squared Error (MSE) of the maximum-likelihood estimator of the time delay is derived. The theoretical predictions align well with simulations and real data.

We propose residual denoising diffusion models (RDDM) a novel dual diffusion process that decouples the traditional single denoising diffusion process into residual diffusion and noise diffusion. This dual diffusion framework expands the denoising-based diffusion models initially uninterpretable for image restoration into a unified and interpretable model for both image generation and restoration by introducing residuals. Specifically our residual diffusion represents directional diffusion from the target image to the degraded input image and explicitly guides the reverse generation process for image restoration while noise diffusion represents random perturbations in the diffusion process. The residual prioritizes certainty while the noise emphasizes diversity enabling RDDM to effectively unify tasks with varying certainty or diversity requirements such as image generation and restoration. We demonstrate that our sampling process is consistent with that of DDPM and DDIM through coefficient transformation and propose a partially path-independent generation process to better understand the reverse process. Notably our RDDM enables a generic UNet trained with only an L1 loss and a batch size of 1 to compete with state-of-the-art image restoration methods. We provide code and pre-trained models to encourage further exploration application and development of our innovative framework (https://github.com/nachifur/RDDM).

Monocular depth estimation is a fundamental computer vision task. Recovering 3D depth from a single image is geometrically ill-posed and requires scene understanding so it is not surprising that the rise of deep learning has led to a breakthrough. The impressive progress of monocular depth estimators has mirrored the growth in model capacity from relatively modest CNNs to large Transformer architectures. Still monocular depth estimators tend to struggle when presented with images with unfamiliar content and layout since their knowledge of the visual world is restricted by the data seen during training and challenged by zero-shot generalization to new domains. This motivates us to explore whether the extensive priors captured in recent generative diffusion models can enable better more generalizable depth estimation. We introduce Marigold a method for affine-invariant monocular depth estimation that is derived from Stable Diffusion and retains its rich prior knowledge. The estimator can be fine-tuned in a couple of days on a single GPU using only synthetic training data. It delivers state-of-the-art performance across a wide range of datasets including over 20% performance gains in specific cases. Project page: https://marigoldmonodepth.github.io.

Humans effortlessly interpret images by parsing them into part-whole hierarchies; deep learning excels in learning multi-level feature spaces but they often lack explicit coding of part-whole relations a prominent property of medical imaging. To overcome this limitation we introduce Adam-v2 a new self-supervised learning framework extending Adam [68] by explicitly incorporating part-whole hierarchies into its learning objectives through three key branches: (1) Localizability acquiring discriminative representations to distinguish different anatomical patterns; (2) Composability learning each anatomical structure in a parts-to-whole manner; and (3) Decomposability comprehending each anatomical structure in a whole-to-parts manner. Experimental results across 10 tasks compared to 11 baselines in zero-shot few-shot transfer and full fine-tuning settings showcase Adam-v2's superior performance over large-scale medical models and existing SSL methods across diverse downstream tasks. The higher generality and robustness of Adam-v2's representations originate from its explicit construction of hierarchies for distinct anatomical structures from unlabeled medical images. Adam-v2 preserves a semantic balance of anatomical diversity and harmony in its embedding yielding representations that are both generic and semantically meaningful yet overlooked in existing SSL methods. All code and pretrained models are available at GitHub.com/JLiangLab/Eden.

Recently lightweight Vision Transformers (ViTs) demonstrate superior performance and lower latency compared with lightweight Convolutional Neural Networks (CNNs) on resource-constrained mobile devices. Researchers have discovered many structural connections between lightweight ViTs and lightweight CNNs. However the notable architectural disparities in the block structure macro and micro designs between them have not been adequately examined. In this study we revisit the efficient design of lightweight CNNs from ViT perspective and emphasize their promising prospect for mobile devices. Specifically we incrementally enhance the mobile-friendliness of a standard lightweight CNN i.e. MobileNetV3 by integrating the efficient architectural designs of lightweight ViTs. This ends up with a new family of pure lightweight CNNs namely RepViT. Extensive experiments show that RepViT outperforms existing state-of-the-art lightweight ViTs and exhibits favorable latency in various vision tasks. Notably on ImageNet RepViT achieves over 80% top-1 accuracy with 1.0 ms latency on an iPhone 12 which is the first time for a lightweight model to the best of our knowledge. Besides when RepViT meets SAM our RepViT-SAM can achieve nearly 10xfaster inference than the advanced MobileSAM. Codes and models are available at https://github.com/THU-MIG/RepViT.

In this work we present RepKPU an efficient network for point cloud upsampling. We propose to promote upsampling performance by exploiting better shape representation and point generation strategy. Inspired by KPConv we propose a novel representation called RepKPoints to effectively characterize the local geometry whose advantages over prior representations are as follows: (1) density-sensitive; (2) large receptive fields; (3) position-adaptive which makes RepKPoints a generalized form of previous representations. Moreover we propose a novel paradigm namely Kernel-to-Displacement generation for point generation where point cloud upsampling is reformulated as the deformation of kernel points. Specifically we propose KP-Queries which is a set of kernel points with predefined positions and learned features to serve as the initial state of upsampling. Using cross-attention mechanisms we achieve interactions between RepKPoints and KP-Queries and subsequently KP-Queries are converted to displacement features followed by a MLP to predict the new positions of KP-Queries which serve as the generated points. Extensive experimental results demonstrate that RepKPU outperforms state-of-the-art methods on several widely-used benchmark datasets with high efficiency.

The simulated annealing algorithm aims to improve model convergence through multiple restarts of training. However existing annealing algorithms overlook the correlation between different cycles neglecting the potential for incremental learning. We contend that a fixed network structure prevents the model from recognizing distinct features at different training stages. To this end we propose RepAn redesigning the irreversible re-parameterization (Rep) method and integrating it with annealing to enhance training. Specifically the network goes through Rep expansion restoration and backpropagation operations during training and iterating through these processes in each annealing round. Such a method exhibits good generalization and is easy to apply and we provide theoretical explanations for its effectiveness. Experiments demonstrate that our method improves baseline performance by 6.38% on the CIFAR-100 dataset and 2.80% on ImageNet achieving state-of-the-art performance in the Rep field. The code is available at https://github.com/xfey/RepAn.

Portrait harmonization aims to composite a subject into a new background adjusting its lighting and color to ensure harmony with the background scene. Existing harmonization techniques often only focus on adjusting the global color and brightness of the foreground and ignore crucial illumination cues from the background such as apparent lighting direction leading to unrealistic compositions. We introduce Relightful Harmonization a lighting-aware diffusion model designed to seamlessly harmonize sophisticated lighting effect for the foreground portrait using any background image. Our approach unfolds in three stages. First we introduce a lighting representation module that allows our diffusion model to encode lighting information from target image background. Second we introduce an alignment network that aligns lighting features learned from image background with lighting features learned from panorama environment maps which is a complete representation for scene illumination. Last to further boost the photorealism of the proposed method we introduce a novel data simulation pipeline that generates synthetic training pairs from a diverse range of natural images which are used to refine the model. Our method outperforms existing benchmarks in visual fidelity and lighting coherence showing superior generalization in real-world testing scenarios highlighting its versatility and practicality.